Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2459 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.5892. Min Act: -0.1700
Data Index: 514294 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.3705. Min Act: -0.1700
Data Index: 3188540 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.3705. Min Act: -0.1700
Data Index: 6287605 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.3080. Min Act: -0.1700
Data Index: 7308067 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2455. Min Act: -0.1700
Data Index: 4848210 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2142. Min Act: -0.1700
Data Index: 6829954 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2142. Min Act: -0.1700
Data Index: 5727402 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2142. Min Act: -0.1700
Data Index: 7975638 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1830. Min Act: -0.1700
Data Index: 7101187 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1517. Min Act: -0.1700
Data Index: 2361628 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1517. Min Act: -0.1700
Data Index: 2092120 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0892. Min Act: -0.1700
Data Index: 7627160 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0892. Min Act: -0.1700
Data Index: 1626780 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0892. Min Act: -0.1700
Data Index: 4832402 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0580. Min Act: -0.1700
Data Index: 5110010 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0580. Min Act: -0.1700
Data Index: 1542299 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0580. Min Act: -0.1700
Data Index: 3138509 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0580. Min Act: -0.1700
Data Index: 7532764 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.0267. Min Act: -0.1700
Data Index: 2104757 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5892. Min Range: -6.5892
Max Act: 5.9955. Min Act: -0.1700
Data Index: 4717871 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19